In this paper, we leverage an exclusive English dataset to train diverse multilingual classifiers, investigating their efficacy in adapting to Finnish data. We employ an exclusively English classification dataset of UN Sustainable Development Goals (SDG) in an education context, to train various multilingual classifiers and examine how well these models can adapt to recognizing the same classes within Finnish university course descriptions. It’s worth noting that Finnish, with a mere 5 million native speakers, presents a significantly less-resourced linguistic context compared to English. The best performing model in our experiments was mBART with an F1-score of 0.843.

We present our work on two LLM-based tools that utilize artificial intelligence and creative technology to improve education. The first tool is a Moodle AI plugin, which helps teachers manage their course content more efficiently using AI-driven analysis, content generation, and an interactive chatbot. The second one is a curriculum planning tool that provides insight into the sustainability, work-life relevance, and workload of each course. Both of these tools have the common goal of integrating sustainable development goals (UN SDGs) into teaching, among other things. We will describe the usability-focused and user-centric approach we have embraced when developing these tools.